Muutke küpsiste eelistusi

E-raamat: Concurrent Reactive Plans: Anticipating and Forestalling Execution Failures

Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 55,56 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

In this book, the author presents a new computational model of forestalling common flaws in autonomous robot behavior. To this end, robots are equipped with structured reactive plans (SRPs) which are concurrent control programs that can not only be interpreted but also be reasoned about and manipulated. The author develops a representation for SRPs in which declarative statements for goals, perceptions, and beliefs make the structure and purpose of SRPs explicit and thereby simplify and speed up reasoning about SRPs and their projections; furthermore a notation is introduced allowing for transforming and manipulating SRPs. Using this notation, a planning system can diagnose and forestall common flaws in robot plans that cannot be dealt with in other planning representations. Finally the language for writing SRPs is extended into a high-level language that can handle both planning and execution actions.

Muu info

Springer Book Archives
Abstract v
Acknowledgements ix
List of Figures
xv
Introduction
1(20)
The Approach
3(3)
Technical Challenges
6(2)
Introductory Example
8(3)
Motivation
11(2)
Relevance for Autonomous Robot Control
11(1)
Relevance for AI Planning
12(1)
The Computational Problem and Its Solution
13(2)
The Computational Problem
13(1)
The Computational Model
14(1)
Contributions
15(4)
Outline of the Book
19(2)
Reactivity
21(26)
The Delivery World
22(6)
The World
22(3)
Commands and Jobs
25(1)
The Robot
26(1)
Justification of the Delivery World
27(1)
The Implementation of Routine Activities
28(12)
Plan Steps vs. Concurrent Control Processes
29(2)
Interfacing Continuous Control Processes
31(2)
Coordinating Control Processes
33(2)
Synchronization of Concurrent Control Threads
35(1)
Failure Recovery
36(1)
Perception
37(1)
State, Memory, and World Models
37(2)
The Structure of Routine Activities
39(1)
The Structured Reactive Controller
40(4)
Behavior and Planning Modules
41(1)
The Body of the Structured Reactive Controller
42(1)
Global Fluents, Variables, and the Plan Library
43(1)
The RPL Runtime System
43(1)
Summary and Discussion
44(3)
Planning
47(28)
The Structured Reactive Plan
47(6)
Plans as Syntactic Objects
48(2)
RPL as a Plan Language
50(3)
The Computational Structure
53(13)
The ``Criticize-Revise'' Cycle
53(2)
The ``Criticize'' Step
55(11)
The ``Revise'' Step
66(1)
The XFRM Planning Framework
66(1)
Anticipation and Forestalling of Behavior Flaws
67(5)
The Detection of Behavior Flaws
68(1)
Behavior Flaws and Plan Revisions
68(1)
The Diagnosis of Behavior Flaws
69(3)
Summary and Discussion
72(3)
Transparent Reactive Plans
75(24)
Declarative Statements
75(13)
RPL Construct Descriptions
78(3)
Achievement Goals
81(2)
Perceptions
83(1)
Beliefs
84(1)
Other Declarative Statements
85(1)
Using Declarative Statements
86(2)
Routine Plans
88(5)
The Plan Library
93(4)
Behavior Modules
93(1)
Low-level Plans
93(2)
High-level Plans
95(2)
Discussion
97(2)
Representing Plan Revisions
99(22)
Conceptualization
101(4)
Making Inferences
105(9)
Some Examples
107(1)
Accessing Code Trees
108(2)
Predicates on Plan Interpretations
110(1)
Predicates on Timelines
111(1)
Timelines and Plan Interpretation
112(2)
Expressing Plan Revisions
114(2)
XFRML---The Implementation
116(1)
Discussion
117(4)
Forestalling Behavior Flaws
121(26)
FAUST
121(14)
The Behavior Critic
121(2)
Detecting Behavior Flaws: Implementation
123(5)
Diagnosing the Causes of Behavior Flaws: Implementation
128(6)
The Bug Class ``Behavior-Specification Violation''
134(1)
The Elimination of Behavior Flaws
135(1)
The Plan Revisions for the Example
135(5)
Some Behavior Flaws and Their Revisions
140(4)
Perceptual Confusion
141(1)
Missed Deadlines
142(2)
Summary and Discussion
144(3)
Planning Ongoing Activities
147(20)
Extending RPL
149(9)
The Runtime-Plan Statement
151(3)
Plan Swapping
154(2)
Making Planning Assumptions
156(2)
Deliberative Controllers
158(5)
Improving Iterative Plans by Local Planning
158(1)
Plan Execution a la Shakey
158(1)
Execution Monitoring and Replanning
159(1)
Recovering from Execution Failures
160(1)
Some Robot Control Architectures
161(2)
The Controller in the Experiment
163(1)
Discussion
164(3)
Evaluation
167(34)
Analysis of the Problem
167(3)
Assessment of the Method
170(6)
Description of the Method
170(1)
Evaluation of the Method
170(6)
Demonstration
176(13)
Evaluating SRCs in Standard Situations
176(3)
Comparing SRCs with the Appropriate Fixed Controller
179(2)
Problems that Require SRCs
181(8)
Related Work
189(12)
Control Architectures for Competent Physical Agents
189(5)
Control Languages for Reactive Control
194(1)
Robot Planning
195(6)
Conclusion
201(4)
What Do Structured Reactive Controllers Do?
201(1)
Why Do Structured Reactive Controllers Work?
202(2)
Do Structured Reactive Controllers Work for Real Robots?
204(1)
References 205